Downloads · 30 days
20
5% of all-time downloads
gemma-qlora-customer-support
RituGujela100/gemma-qlora-customer-support
gemma-qlora-customer-support is a text generation model from RituGujela100. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
All-time downloads
432
Public
Parameters
2.5B
5.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5 GB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- gemma
- Access
- Public
- Created
- Apr 23, 2025
- Updated
- Apr 29, 2025
- SHA
- 3fa8ac0c
Try a prompt
Base models
Model card
From the Hugging Face model README
license: mit
Gemma 2B IT - Customer Support Fine-tuned Model (QLoRA)
This model is a fine-tuned version of google/gemma-1.1-2b-it
using QLoRA on a custom instruction-tuning dataset designed for automating customer support tasks, including:
- ✉️ Complaint summarization
- 💬 Sentiment analysis
- 🧠 Topic modeling
- 📉 Churn prediction
- 🧾 Auto response drafting
🛠 Fine-tuning Details
- Technique: QLoRA (4-bit quantization using
bitsandbytes) - Dataset: 14k+ records combining Amazon review and Q&A data
- Data format: ChatML-style JSONL with
messages: [{role: ..., content: ...}] - Training platform: Google Colab (A100 GPU)
- Libraries: Hugging Face
transformers,peft,datasets
💡 Use Cases
This model is best suited for:
- Automating customer support replies using auto-response drafting
- Summarizing customer complaints to understand the needs better
- Classifying topics and customer sentiments
- Predicting churn based on interaction tone and topics
- Task
- Text Generation
- Library
- transformers
- Type
- gemma
- License
- mit
- Languages
- en
- Created
- Apr 23, 2025
- Updated
- Apr 29, 2025